The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 14, 2016

Filed:

Jan. 12, 2015
Applicant:

Xerox Corporation, Norwalk, CT (US);

Inventors:

Albert Gordo Soldevila, Grenoble, FR;

Florent C. Perronnin, Domène, FR;

Assignee:

XEROX CORPORATION, Norwalk, CT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06K 9/62 (2006.01); G06K 9/18 (2006.01); G06K 9/52 (2006.01); G06K 9/32 (2006.01); G06F 17/30 (2006.01); G06F 21/60 (2013.01); G06F 17/11 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6201 (2013.01); G06F 17/11 (2013.01); G06F 17/3053 (2013.01); G06F 17/30244 (2013.01); G06F 21/60 (2013.01); G06K 9/18 (2013.01); G06K 9/325 (2013.01); G06K 9/52 (2013.01); G06K 9/627 (2013.01); G06K 9/6256 (2013.01); G06K 9/6267 (2013.01);
Abstract

A method for text-to-image matching includes generating representations of text images, such as license plate images, by embedding each text image into a first vectorial space with a first embedding function. With a second embedding function, a character string, such as a license plate number to be matched, is embedded into a second vectorial space to generate a character string representation. A compatibility is computed between the character string representation and one or more of the text image representations to identify a matching one. The compatibility is computed with a function that uses a transformation which is learned on a training set of labeled images. The learning uses a loss function that aggregates a text-to-image-loss and an image-to-text loss over the training set. The image-to-text loss penalizes the transformation when it correctly ranks a pair of character string representations, given an image representation corresponding to one of them.


Find Patent Forward Citations

Loading…